9 datasets found

The Multi30k dataset is an extension of the Flickr30k dataset, containing 29,000 train images, 1,014 validation images and 1,000 test images. Each image is accompanied with six...

The dataset used in the paper is COCO captions and Localized Narratives, which are used to generate image descriptions.

The dataset used in the paper is VQA-CP v2 and VQA 2.0, which are two standard datasets for visual question answering.

The VQA 2.0 dataset is used for visual question answering task. It consists of three sets with a train set containing 83k images and 444k questions, a validation set containing...

The Flickr30k dataset is widely utilized for image caption and image-text retrieval tasks, providing a substantial collection of images with associated captions.

Large scale datasets [18, 17, 27, 6] boosted text conditional image generation quality. However, in some domains it could be difficult to make such datasets and usually it could...

Visual Story-Telling dataset (VIST) is the only publicly accessible dataset for storytelling problems. It comprises 210,819 distinct images that can be found in 10,117 different...

Large scale datasets [18, 17, 27, 6] boosted text conditional image generation quality. However, in some domains it could be difficult to make such datasets and usually it could...

Human Pose Estimation (HPE) aims to estimate the position of each joint point of the human body in a given image. HPE tasks support a wide range of downstream tasks such as...